search

Ha0Tang / SelectionGAN

[CVPR 2019 Oral] Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation
http://disi.unitn.it/~hao.tang/project/SelectionGAN.html
460 stars 63 forks source link

sharpness difference #3

Closed hluo29 closed 4 years ago

hluo29 commented 4 years ago

Hello, could you provide the sharpness difference evaluation code? Thanks

Ha0Tang commented 4 years ago

Please refer here https://github.com/Ha0Tang/SelectionGAN/blob/master/scripts/evaluation/compute_ssim_psnr_sharpness.lua

hluo29 commented 4 years ago

Thanks a lot.

hluo29 commented 4 years ago

In the paper, you mean 'C outperforms A with 8.19, F outperforms E with 4.67 on ssim', actually they are 0.0819 and 0.0467. How to understand?

Ha0Tang commented 4 years ago

It means Baseline F outperforms E with around 4.67 points gain on the SSIM metric. In other words, you can multiply each value by 100.

hluo29 commented 4 years ago

ok, thanks